DisparateVulnerability
Disparate Vulnerability to Membership Inference Attacks
A membership inference attack (MIA) against a machine-learning model enables an attacker to determine whether a given data record was part of the model's training data or not. DisparateVulnerability helps in measuring how much a given model can be inverted.
inactive
—
entered showcase: 2022-07-07
—
entry updated: 2022-08-11
Prototype
Simulation, Experiments
Python
MIT